GPT-6.2 Astra panned by top reviewers: 'essentially unusable,' falls short of Opus 5.5 and Fable
deedydas · x · 2026-11-18
Deedy compiled negative first reviews of OpenAI's GPT-6.2 Astra / Sol, calling the launch "a massive fail for every critic that has reviewed it":
- Theo (t3.gg): early testing frustrated him enough to write a formal letter to OpenAI; only a handful of complaints were fixed, still not recommendable
- Matt Shumer: declined to write a full review — "a terrible experience testing them. They were essentially unusable"
- Matthew Berman: the models are "good" but clearly below Opus 5.5 and Fable; OpenAI came up short
- Ben Davis: capable (strong 3D work, quality code) but horrible at communicating reasoning — gives hollow 20-paragraph essays, is lazy, and lacks the taste of Opus 5.5 / Fable 5.2, which are 10-20% more capable and 20x more pleasant to work with
A classic launch of decent benchmarks but poor in-hand experience.
More from Models
- GPT-6.2 Astra and Sol roll out as testers push back on the hate wave — jeffintime · 2026-11-18
- GPT 6.2 Astra and Sol Take 4th and 5th on sudo L7 Coding Benchmark, Still Behind Latest Claude — echen · 2026-11-18
- Why did OpenAI ship a dud? Ex-engineer suspects cost-cut bet on RL backfired — doodlestein · 2026-11-18
- No single model matches Claude, says developer as Anthropic 'hits escape velocity' — _arohan_ · 2026-11-18
- Hands-on with GPT-6.2: Ignore the hate, it's a cheap computer-use workhorse — nickbaumann_ · 2026-11-18
- Claude leads Arena agent leaderboard with nearly 2x praise-to-complaint ratio — thursdai_pod · 2026-11-18